Deep representation learning of chemical-induced transcriptional profile for phenotype-based drug discovery.
Xiaochu TongNing QuXiangtai KongShengkun NiJingyi ZhouKun WangLehan ZhangYiming WenJiangshan ShiSulin ZhangXutong LiMingyue ZhengPublished in: Nature communications (2024)
Artificial intelligence transforms drug discovery, with phenotype-based approaches emerging as a promising alternative to target-based methods, overcoming limitations like lack of well-defined targets. While chemical-induced transcriptional profiles offer a comprehensive view of drug mechanisms, inherent noise often obscures the true signal, hindering their potential for meaningful insights. Here, we highlight the development of TranSiGen, a deep generative model employing self-supervised representation learning. TranSiGen analyzes basal cell gene expression and molecular structures to reconstruct chemical-induced transcriptional profiles with high accuracy. By capturing both cellular and compound information, TranSiGen-derived representations demonstrate efficacy in diverse downstream tasks like ligand-based virtual screening, drug response prediction, and phenotype-based drug repurposing. Notably, in vitro validation of TranSiGen's application in pancreatic cancer drug discovery highlights its potential for identifying effective compounds. We envisage that integrating TranSiGen into the drug discovery and mechanism research holds significant promise for advancing biomedicine.
Keyphrases
- drug discovery
- gene expression
- artificial intelligence
- high glucose
- drug induced
- machine learning
- diabetic rats
- big data
- transcription factor
- working memory
- dna methylation
- emergency department
- oxidative stress
- single cell
- heat shock
- bone marrow
- endothelial cells
- mass spectrometry
- cell therapy
- health information
- mesenchymal stem cells
- heat stress
- climate change
- heat shock protein